This function performs the random skewers matrix comparison method of Cheverud (1996; also see Cheverud & Marroig 2007 for more details). In addition, it includes a more robust hypothesis test in which random covariance matrices are simulated under a variety of models, and then the mean correlation between response vectors to random skewers are computed.
skewers(X, Y, nsim=100, method=NULL)A list with the following components:
mean random skewers correlation.
p-value from simulation.
covariance matrix.
covariance matrix.
number of random vectors.
method to generate a null distribution of the random skewers correlation between matrices. If method=NULL then the correlation will be compared to the correlation between random vectors; however this test has type I error substantially above the nominal level for ostensibly random matrices. Other values of method will be passed as covMethod to genPositiveDefMat for a more robust hypothesis test (see below). Recommended values include "unifcorrmat".
Liam Revell liam.revell@umb.edu
Cheverud, J. M. (1996) Quantitative genetic analysis of cranial morphology in the cotton-top (Saguinus oedipus) and saddle-back (S. fuscicollis) tamarins. J. Evol. Biol., 9, 5--42.
Cheverud, J. M. & Marroig, G. (2007) Comparing covariance matrices: Random skewers method compared to the common principal components model. Genetics & Molecular Biology, 30, 461--469.
Revell, L. J. (2012) phytools: An R package for phylogenetic comparative biology (and other things). Methods Ecol. Evol., 3, 217-223.